© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1179
    Prev
    Next
    INDEX
    Explanations

    sea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sea
    -0.93
     Sea
    -0.91
    Sea
    -0.78
     SEA
    -0.61
    sea
    -0.52
    海
    -0.47
    SEA
    -0.47
    例句
    -0.46
     Cohen
    -0.44
     dry
    -0.42
    POSITIVE LOGITS
    出版年
    0.79
    onViewCreated
    0.73
    weeds
    0.71
    BeginContext
    0.70
     peony
    0.68
    ActionCreators
    0.67
     Exacts
    0.66
    kháu
    0.65
    getSeconds
    0.65
     weevil
    0.64
    Activations Density 0.388%

    No Known Activations